Related papers: A Useful Motif for Flexible Task Learning in an Em…

Visual navigation is a task of training an embodied agent by intelligently navigating to a target object (e.g., television) using only visual observations. A key challenge for current deep reinforcement learning models lies in the…

Evaluating the generalisation capabilities of multimodal models based solely on their performance on out-of-distribution data fails to capture their true robustness. This work introduces a comprehensive evaluation framework that…

Humans are highly efficient learners, with the ability to grasp the meaning of a new concept from just a few examples. Unlike popular computer vision systems, humans can flexibly leverage the compositional structure of the visual world,…

Diverse studies in systems neuroscience begin with extended periods of curriculum training known as `shaping' procedures. These involve progressively studying component parts of more complex tasks, and can make the difference between…

The rapid evolution of machine learning has propelled neural networks to unprecedented success across diverse domains. In particular, multimodal learning has emerged as a transformative paradigm, leveraging complementary information from…

Embodied Artificial Intelligence (AI) is an intelligent system formed by agents and their environment through active perception, embodied cognition, and action interaction. Existing embodied AI remains confined to human-crafted setting, in…

The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI. Here, we consider tests of out-of-sample generalisation that…

The ability to act in multiple environments and transfer previous knowledge to new situations can be considered a critical aspect of any intelligent agent. Towards this goal, we define a novel method of multitask and transfer learning that…

Recent work in sim2real has successfully enabled robots to act in physical environments by training in simulation with a diverse ''population'' of environments (i.e. domain randomization). In this work, we focus on enabling generalization…

Developing a generalist agent is a longstanding objective in artificial intelligence. Previous efforts utilizing extensive offline datasets from various tasks demonstrate remarkable performance in multitasking scenarios within Reinforcement…

Multi-task learning has recently emerged as a promising solution for a comprehensive understanding of complex scenes. In addition to being memory-efficient, multi-task models, when appropriately designed, can facilitate the exchange of…

For humans, visual understanding is inherently generative: given a 3D shape, we can postulate how it would look in the world; given a 2D image, we can infer the 3D structure that likely gave rise to it. We can thus translate between the 2D…

We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons. We apply this mechanism in the framework…

We explore the behavior of a standard convolutional neural net in a continual-learning setting that introduces visual classification tasks sequentially and requires the net to master new tasks while preserving mastery of previously learned…

This paper tackles the problem of how to pre-train a model and make it generally reusable backbones for downstream task learning. In pre-training, we propose a method that builds an agent-environment interaction model by learning domain…

Training a neural network is a monolithic endeavor, akin to carving knowledge into stone: once the process is completed, editing the knowledge in a network is hard, since all information is distributed across the network's weights. We here…

Data-driven approaches to tactile sensing aim to overcome the complexity of accurately modeling contact with soft materials. However, their widespread adoption is impaired by concerns about data efficiency and the capability to generalize…

Embodied intelligence aims to enable robots to learn, reason, and generalize robustly across complex real-world environments. However, existing approaches often struggle with partial observability, fragmented spatial reasoning, and…

Manipulation of deformable objects is a challenging task for a robot. It will be problematic to use a single sensory input to track the behaviour of such objects: vision can be subjected to occlusions, whereas tactile inputs cannot capture…

Active recognition enables robots to intelligently explore novel observations, thereby acquiring more information while circumventing undesired viewing conditions. Recent approaches favor learning policies from simulated or collected data,…